{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T06:22:47Z","timestamp":1774160567867,"version":"3.50.1"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072230"],"award-info":[{"award-number":["62072230"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272223"],"award-info":[{"award-number":["62272223"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Province Science and Technology Key Program","award":["BE2021729"],"award-info":[{"award-number":["BE2021729"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["020214380089"],"award-info":[{"award-number":["020214380089"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["020214380098"],"award-info":[{"award-number":["020214380098"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["020214912216"],"award-info":[{"award-number":["020214912216"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Collaborative Innovation Center of Novel Software Technology and Industrialization"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1109\/tpds.2023.3314659","type":"journal-article","created":{"date-parts":[[2023,9,12]],"date-time":"2023-09-12T17:37:29Z","timestamp":1694540249000},"page":"2946-2964","source":"Crossref","is-referenced-by-count":7,"title":["High-Level Data Abstraction and Elastic Data Caching for Data-Intensive AI Applications on Cloud-Native Platforms"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1565-9997","authenticated-orcid":false,"given":"Rong","family":"Gu","sequence":"first","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}]},{"given":"Zhihao","family":"Xu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, Zhejiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8220-1912","authenticated-orcid":false,"given":"Yang","family":"Che","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, Zhejiang, China"}]},{"given":"Xu","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0545-8187","authenticated-orcid":false,"given":"Haipeng","family":"Dai","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}]},{"given":"Kai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, Zhejiang, China"}]},{"given":"Bin","family":"Fan","sequence":"additional","affiliation":[{"name":"Alluxio. Inc., San Mateo, CA, USA"}]},{"given":"Haojun","family":"Hou","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}]},{"given":"Li","family":"Yi","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, Zhejiang, China"}]},{"given":"Yu","family":"Ding","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, Zhejiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1806-0936","authenticated-orcid":false,"given":"Yihua","family":"Huang","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6934-1685","authenticated-orcid":false,"given":"Guihai","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/PDSW-DISCS.2018.00011"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3404397.3404472"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00018"},{"key":"ref34","first-page":"1","article-title":"Hoard: A distributed data caching system to accelerate deep learning training on the cloud","volume":"6","author":"pinto","year":"2018","journal-title":"Comput Res Repository"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOTS.2018.00023"},{"key":"ref37","first-page":"485","article-title":"Tiresias: A GPU cluster manager for distributed deep learning","author":"gu","year":"2019","journal-title":"Proc 16th USENIX Symp Networked Syst Des Implementation"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2019.00037"},{"key":"ref36","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","author":"xiao","year":"2018","journal-title":"Proc 13th USENIX Symp Operating Syst Des Implementation"},{"key":"ref31","article-title":"Pytorch data loading utility","year":"2023"},{"key":"ref30","first-page":"1","article-title":"Faster neural network training with data echoing","volume":"55","author":"choi","year":"2019","journal-title":"Comput Res Repository"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3047974"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW52791.2021.00127"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2019.8891012"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.14778\/3476311.3476374"},{"key":"ref2","article-title":"Google announces a new generation for its TPU machine learning hardware","author":"linley","year":"2018"},{"key":"ref1","article-title":"NVIDIA A100 tensor core GPU architecture","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3064966"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref16","article-title":"Torchelastic controller for kubernetes","year":"2020"},{"key":"ref38","first-page":"579","article-title":"Looking beyond gpus for DNN scheduling on multi-tenant clusters","author":"mohan","year":"2022","journal-title":"Proc 16th USENIX Symp Operating Syst Des Implementation"},{"key":"ref19","article-title":"Persistent volume","year":"0"},{"key":"ref18","first-page":"15","article-title":"Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing","author":"zaharia","year":"2012","journal-title":"Proc 9th USENIX Symp Networked Syst Des Implementation"},{"key":"ref24","article-title":"Operator pattern","year":"2023"},{"key":"ref23","first-page":"283","article-title":"Quiver: An informed storage cache for deep learning","author":"kumar","year":"2020","journal-title":"Proc 18th USENIX Conf File Storage Technol"},{"key":"ref26","article-title":"Controller","year":"2023"},{"key":"ref25","article-title":"Custom resource definition","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2670979.2670985"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00209"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.17487\/rfc5681"},{"key":"ref21","article-title":"HDFS architecture","year":"2022"},{"key":"ref28","first-page":"515","article-title":"HiveD: Sharing a GPU cluster for deep learning with guarantees","author":"zhao","year":"2020","journal-title":"Proc 14th USENIX Symp Operating Syst Des Implementation"},{"key":"ref27","article-title":"Container storage interface (CSI)","year":"2023"},{"key":"ref29","article-title":"Fast AI data preprocessing with NVIDIA DALI","year":"2019"},{"key":"ref8","first-page":"1","article-title":"Clairvoyant prefetching for distributed machine learning I\/O","author":"b\u00f6hringer","year":"2021","journal-title":"Proc 34th Int Conf High Perform Comput Netw Storage Anal"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2890784"},{"key":"ref9","first-page":"1","article-title":"Analyzing and mitigating data stalls in DNN training","volume":"67","author":"mohan","year":"2020","journal-title":"Comput Res Repository"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2979670"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.102805"},{"key":"ref6","first-page":"2","article-title":"Docker: Lightweight linux containers for consistent development and deployment","volume":"2014","author":"merkel","year":"2014","journal-title":"Linux J"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.array.2019.100004"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3138825"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/10248992\/10249214.pdf?arnumber=10249214","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,16]],"date-time":"2023-10-16T18:30:00Z","timestamp":1697481000000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10249214\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11]]},"references-count":41,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2023.3314659","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11]]}}}